Vehicle Detection - Gaspard Shen¶
1. HOG¶
Read the Vehicles and non-Vehicles training images set¶
In [1]:
import numpy as np
import cv2
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import glob
#from skimage.feature import hog
#from skimage import color, exposure
# images are divided up into vehicles and non-vehicles
cars = []
images = glob.glob('vehicles/**/*.png')
for image in images:
cars.append(image)
notcars = []
images = glob.glob('non-vehicles/**/*.png')
for image in images:
notcars.append(image)
# Define a function to return some characteristics of the dataset
def data_look(car_list, notcar_list):
data_dict = {}
# Define a key in data_dict "n_cars" and store the number of car images
data_dict["n_cars"] = len(car_list)
# Define a key "n_notcars" and store the number of notcar images
data_dict["n_notcars"] = len(notcar_list)
# Read in a test image, either car or notcar
example_img = mpimg.imread(car_list[0])
# Define a key "image_shape" and store the test image shape 3-tuple
data_dict["image_shape"] = example_img.shape
# Define a key "data_type" and store the data type of the test image.
data_dict["data_type"] = example_img.dtype
# Return data_dict
return data_dict
data_info = data_look(cars, notcars)
print('Your function returned a count of',
data_info["n_cars"], ' cars and',
data_info["n_notcars"], ' non-cars')
print('of size: ',data_info["image_shape"], ' and data type:',
data_info["data_type"])
for i in range(6):
# Just for fun choose random car / not-car indices and plot example images
car_ind = np.random.randint(0, len(cars))
notcar_ind = np.random.randint(0, len(notcars))
# Read in car / not-car images
#print(cars[car_ind], notcars[notcar_ind])
car_image = mpimg.imread(cars[car_ind])
notcar_image = mpimg.imread(notcars[notcar_ind])
# Plot the examples
fig = plt.figure(figsize=(10, 12))
plt.subplot(121)
plt.imshow(car_image)
plt.title(cars[car_ind])
plt.subplot(122)
plt.imshow(notcar_image)
plt.title(notcars[notcar_ind])
plt.show()
Tuning the HOG Parameters¶
In [2]:
from skimage.feature import hog
# Define a function to return HOG features and visualization
def get_hog_features(img, orient, pix_per_cell, cell_per_block, vis=False, feature_vec=True):
if vis == True:
# Use skimage.hog() to get both features and a visualization
features, hog_image = hog(img, orientations=orient,
pixels_per_cell=(pix_per_cell, pix_per_cell),
cells_per_block=(cell_per_block, cell_per_block),
transform_sqrt=False, visualise=True, feature_vector=feature_vec)
return features, hog_image
else:
# Use skimage.hog() to get features only
features= hog(img, orientations=orient,
pixels_per_cell=(pix_per_cell, pix_per_cell),
cells_per_block=(cell_per_block, cell_per_block),
transform_sqrt=False, visualise=False, feature_vector=feature_vec)
return features
def convert_color(img, conv='RGB2YCrCb'):
if conv == 'RGB2GRAY':
return cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
if conv == 'RGB2YCrCb':
return cv2.cvtColor(img, cv2.COLOR_RGB2YCrCb)
if conv == 'RGB2LUV':
return cv2.cvtColor(img, cv2.COLOR_RGB2LUV)
if conv == 'RGB2YUV':
return cv2.cvtColor(img, cv2.COLOR_RGB2YUV)
if conv == 'RGB2HSV':
return cv2.cvtColor(img, cv2.COLOR_RGB2HSV)
if conv == 'RGB2HLS':
return cv2.cvtColor(img, cv2.COLOR_RGB2HLS)
def ShowCarNonCarHOG(img_car, img_notcar, colorspace='RGB2GRAY', orient=9, pix_per_cell=8, cell_per_block=2):
color_carimg = convert_color(img_car, colorspace)
color_carnotimg = convert_color(img_notcar, colorspace)
# Call our function with vis=True to see an image output
features, hog_carimg = get_hog_features(color_carimg, orient,
pix_per_cell, cell_per_block,
vis=True, feature_vec=False)
features, hog_notcarimg = get_hog_features(color_carnotimg, orient,
pix_per_cell, cell_per_block,
vis=True, feature_vec=False)
print('Using: ', colorspace, orient, 'orientation ', pix_per_cell, 'pix_per_cell ', cell_per_block, 'cell_per_bap')
# Plot the examples
fig = plt.figure(figsize=(18, 5))
plt.subplot(141)
plt.imshow(color_carimg, cmap='gray')
plt.title('Car Image')
plt.subplot(142)
plt.imshow(hog_carimg, cmap='gray')
plt.title('HOG Visualization')
plt.subplot(143)
plt.imshow(color_carnotimg, cmap='gray')
plt.title('Non Car Image')
plt.subplot(144)
plt.imshow(hog_notcarimg, cmap='gray')
plt.title('HOG Visualization')
plt.show()
# Generate a random index to look at a car image
ind = np.random.randint(0, len(cars))
car_img = mpimg.imread(cars[ind])
ind = np.random.randint(0, len(notcars))
notcar_img = mpimg.imread(notcars[ind])
# Define HOG parameters
orient = 9
pix_per_cell = 8
cell_per_block = 2
colorspace = 'RGB2GRAY'
ShowCarNonCarHOG(car_img, notcar_img, colorspace, orient, pix_per_cell, cell_per_block)
orient = 12
pix_per_cell = 8
cell_per_block = 2
colorspace = 'RGB2GRAY'
ShowCarNonCarHOG(car_img, notcar_img, colorspace, orient, pix_per_cell, cell_per_block)
# Play the pix_per_cell param
orient = 10
pix_per_cell = 16
cell_per_block = 2
colorspace = 'RGB2GRAY'
ShowCarNonCarHOG(car_img, notcar_img, colorspace, orient, pix_per_cell, cell_per_block)
orient = 11
pix_per_cell = 4
cell_per_block = 2
colorspace = 'RGB2GRAY'
ShowCarNonCarHOG(car_img, notcar_img, colorspace, orient, pix_per_cell, cell_per_block)
Combine and Normalize Features¶
In [3]:
import time
from sklearn.preprocessing import StandardScaler
# Define a function to compute binned color features
def bin_spatial(img, size=(32, 32)):
# Use cv2.resize().ravel() to create the feature vector
features = cv2.resize(img, size).ravel()
# Return the feature vector
return features
# Define a function to compute color histogram features
def color_hist(img, nbins=32, bins_range=(0, 256)):
# Compute the histogram of the color channels separately
channel1_hist = np.histogram(img[:,:,0], bins=nbins, range=bins_range)
channel2_hist = np.histogram(img[:,:,1], bins=nbins, range=bins_range)
channel3_hist = np.histogram(img[:,:,2], bins=nbins, range=bins_range)
# Concatenate the histograms into a single feature vector
hist_features = np.concatenate((channel1_hist[0], channel2_hist[0], channel3_hist[0]))
# Return the individual histograms, bin_centers and feature vector
return hist_features
# Define a function to extract features from a list of images
# Have this function call bin_spatial() and color_hist()
def extract_features(imgs, color_space='RGB', spatial_size=(32, 32),
hist_bins=32, orient=9,
pix_per_cell=8, cell_per_block=2, hog_channel=0,
spatial_feat=True, hist_feat=True, hog_feat=True):
# Create a list to append feature vectors to
features = []
# Iterate through the list of images
for file in imgs:
file_features = []
# Read in each one by one
image = mpimg.imread(file)
# apply color conversion if other than 'RGB'
if color_space != 'RGB':
if color_space == 'HSV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)
elif color_space == 'LUV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2LUV)
elif color_space == 'HLS':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)
elif color_space == 'YUV':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YUV)
elif color_space == 'YCrCb':
feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YCrCb)
else: feature_image = np.copy(image)
if spatial_feat == True:
spatial_features = bin_spatial(feature_image, size=spatial_size)
file_features.append(spatial_features)
if hist_feat == True:
# Apply color_hist()
hist_features = color_hist(feature_image, nbins=hist_bins)
file_features.append(hist_features)
if hog_feat == True:
# Call get_hog_features() with vis=False, feature_vec=True
if hog_channel == 'ALL':
hog_features = []
for channel in range(feature_image.shape[2]):
hog_features.append(get_hog_features(feature_image[:,:,channel],
orient, pix_per_cell, cell_per_block,
vis=False, feature_vec=True))
hog_features = np.ravel(hog_features)
else:
hog_features = get_hog_features(feature_image[:,:,hog_channel], orient,
pix_per_cell, cell_per_block, vis=False, feature_vec=True)
# Append the new feature vector to the features list
file_features.append(hog_features)
features.append(np.concatenate(file_features))
# Return list of feature vectors
return features
### TODO: Tweak these parameters and see how the results change.
colorspace = 'YUV' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
orient = 9
pix_per_cell = 8
cell_per_block = 2
hog_channel = 'ALL' # Can be 0, 1, 2, or "ALL"
t=time.time()
car_features = extract_features(cars, color_space=colorspace, orient=orient,
pix_per_cell=pix_per_cell, cell_per_block=cell_per_block,
hog_channel=hog_channel)
notcar_features = extract_features(notcars, color_space=colorspace, orient=orient,
pix_per_cell=pix_per_cell, cell_per_block=cell_per_block,
hog_channel=hog_channel)
t2 = time.time()
print(round(t2-t, 2), 'Seconds to extract HOG features...')
if len(car_features) > 0:
# Create an array stack of feature vectors
X = np.vstack((car_features, notcar_features)).astype(np.float64)
# Fit a per-column scaler
X_scaler = StandardScaler().fit(X)
# Apply the scaler to X
scaled_X = X_scaler.transform(X)
car_ind = np.random.randint(0, len(cars))
# Plot an example of raw and scaled features
fig = plt.figure(figsize=(12,4))
plt.subplot(131)
plt.imshow(mpimg.imread(cars[car_ind]))
plt.title('Original Image')
plt.subplot(132)
plt.plot(X[car_ind])
plt.title('Raw Features')
plt.subplot(133)
plt.plot(scaled_X[car_ind])
plt.title('Normalized Features')
fig.tight_layout()
plt.show()
else:
print('Your function only returns empty feature vectors...')
2. Train Classifier¶
In [4]:
from sklearn.svm import LinearSVC
from sklearn import grid_search
# NOTE: the next import is only valid for scikit-learn version <= 0.17
# for scikit-learn >= 0.18 use:
# from sklearn.model_selection import train_test_split
from sklearn.cross_validation import train_test_split
# Create an array stack of feature vectors
X = np.vstack((car_features, notcar_features)).astype(np.float64)
# Fit a per-column scaler
X_scaler = StandardScaler().fit(X)
# Apply the scaler to X
scaled_X = X_scaler.transform(X)
# Define the labels vector
y = np.hstack((np.ones(len(car_features)), np.zeros(len(notcar_features))))
# Split up data into randomized training and test sets
rand_state = np.random.randint(0, 100)
X_train, X_test, y_train, y_test = train_test_split(
scaled_X, y, test_size=0.2, random_state=rand_state)
print('Using:',orient,'orientations',pix_per_cell,
'pixels per cell and', cell_per_block,'cells per block')
print('Feature vector length:', len(X_train[0]))
# Use a linear SVC
svc = LinearSVC()
t=time.time()
svc.fit(X_train, y_train)
t2 = time.time()
print(round(t2-t, 2), 'Seconds to train SVC...')
# Check the score of the SVC
print('Test Accuracy of SVC = ', round(svc.score(X_test, y_test), 4))
# Check the prediction time for a single sample
t=time.time()
n_predict = 10
print('My SVC predicts: ', svc.predict(X_test[0:n_predict]))
print('For these',n_predict, 'labels: ', y_test[0:n_predict])
t2 = time.time()
print(round(t2-t, 5), 'Seconds to predict', n_predict,'labels with SVC')
3. Sliding Window Implement¶
Implement the draw_boxes() and slide_window()¶
In [5]:
# Here is your draw_boxes function from the previous exercise
def draw_boxes(img, bboxes, color=(0, 0, 255), thick=6):
# Make a copy of the image
imcopy = np.copy(img)
# Iterate through the bounding boxes
for bbox in bboxes:
# Draw a rectangle given bbox coordinates
cv2.rectangle(imcopy, bbox[0], bbox[1], color, thick)
# Return the image copy with boxes drawn
return imcopy
# Define a function that takes an image,
# start and stop positions in both x and y,
# window size (x and y dimensions),
# and overlap fraction (for both x and y)
def slide_window(img, x_start_stop=[None, None], y_start_stop=[None, None],
xy_window=(64, 64), xy_overlap=(0.5, 0.5)):
# If x and/or y start/stop positions not defined, set to image size
if x_start_stop[0] == None:
x_start_stop[0] = 0
if x_start_stop[1] == None:
x_start_stop[1] = img.shape[1]
if y_start_stop[0] == None:
y_start_stop[0] = 0
if y_start_stop[1] == None:
y_start_stop[1] = img.shape[0]
# Compute the span of the region to be searched
xspan = x_start_stop[1] - x_start_stop[0]
yspan = y_start_stop[1] - y_start_stop[0]
# Compute the number of pixels per step in x/y
nx_pix_per_step = np.int(xy_window[0]*(1 - xy_overlap[0]))
ny_pix_per_step = np.int(xy_window[1]*(1 - xy_overlap[1]))
# Compute the number of windows in x/y
nx_buffer = np.int(xy_window[0]*(xy_overlap[0]))
ny_buffer = np.int(xy_window[1]*(xy_overlap[1]))
nx_windows = np.int((xspan-nx_buffer)/nx_pix_per_step)
ny_windows = np.int((yspan-ny_buffer)/ny_pix_per_step)
# Initialize a list to append window positions to
window_list = []
# Loop through finding x and y window positions
# Note: you could vectorize this step, but in practice
# you'll be considering windows one by one with your
# classifier, so looping makes sense
for ys in range(ny_windows):
for xs in range(nx_windows):
# Calculate window position
startx = xs*nx_pix_per_step + x_start_stop[0]
endx = startx + xy_window[0]
starty = ys*ny_pix_per_step + y_start_stop[0]
endy = starty + xy_window[1]
# Append window position to list
window_list.append(((startx, starty), (endx, endy)))
# Return the list of windows
return window_list
image = mpimg.imread('cutouts/bbox-example-image.jpg')
windows = slide_window(image, x_start_stop=[None, None], y_start_stop=[None, None],
xy_window=(128, 128), xy_overlap=(0.5, 0.5))
window_img = draw_boxes(image, windows, color=(0, 0, 255), thick=6)
plt.imshow(window_img)
plt.show()
Implement the single_img_features¶
In [6]:
# Define a function to extract features from a single image window
# This function is very similar to extract_features()
# just for a single image rather than list of images
def single_img_features(img, color_space='RGB', spatial_size=(32, 32),
hist_bins=32, orient=9,
pix_per_cell=8, cell_per_block=2, hog_channel=0,
spatial_feat=True, hist_feat=True, hog_feat=True):
#1) Define an empty list to receive features
img_features = []
#2) Apply color conversion if other than 'RGB'
if color_space != 'RGB':
if color_space == 'HSV':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2HSV)
elif color_space == 'LUV':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2LUV)
elif color_space == 'HLS':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2HLS)
elif color_space == 'YUV':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2YUV)
elif color_space == 'YCrCb':
feature_image = cv2.cvtColor(img, cv2.COLOR_RGB2YCrCb)
else: feature_image = np.copy(img)
#3) Compute spatial features if flag is set
if spatial_feat == True:
spatial_features = bin_spatial(feature_image, size=spatial_size)
#4) Append features to list
img_features.append(spatial_features)
#5) Compute histogram features if flag is set
if hist_feat == True:
hist_features = color_hist(feature_image, nbins=hist_bins)
#6) Append features to list
img_features.append(hist_features)
#7) Compute HOG features if flag is set
if hog_feat == True:
if hog_channel == 'ALL':
hog_features = []
for channel in range(feature_image.shape[2]):
hog_features.extend(get_hog_features(feature_image[:,:,channel],
orient, pix_per_cell, cell_per_block,
vis=False, feature_vec=True))
else:
hog_features = get_hog_features(feature_image[:,:,hog_channel], orient,
pix_per_cell, cell_per_block, vis=False, feature_vec=True)
#8) Append features to list
img_features.append(hog_features)
#9) Return concatenated array of features
return np.concatenate(img_features)
# Define a function you will pass an image
# and the list of windows to be searched (output of slide_windows())
def search_windows(img, windows, clf, scaler, color_space='RGB',
spatial_size=(32, 32), hist_bins=32,
hist_range=(0, 256), orient=9,
pix_per_cell=8, cell_per_block=2,
hog_channel=0, spatial_feat=True,
hist_feat=True, hog_feat=True):
#1) Create an empty list to receive positive detection windows
on_windows = []
#2) Iterate over all windows in the list
for window in windows:
#3) Extract the test window from original image
test_img = cv2.resize(img[window[0][1]:window[1][1], window[0][0]:window[1][0]], (64, 64))
#4) Extract features for that window using single_img_features()
features = single_img_features(test_img, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
#5) Scale extracted features to be fed to classifier
test_features = scaler.transform(np.array(features).reshape(1, -1))
#6) Predict using your classifier
prediction = clf.predict(test_features)
#7) If positive (prediction == 1) then save the window
if prediction == 1:
on_windows.append(window)
#8) Return windows for positive detections
return on_windows
### TODO: Tweak these parameters and see how the results change.
color_space = 'YUV' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb
orient = 9 # HOG orientations
pix_per_cell = 8 # HOG pixels per cell
cell_per_block = 2 # HOG cells per block
hog_channel = "ALL" # Can be 0, 1, 2, or "ALL"
spatial_size = (32, 32) # Spatial binning dimensions
hist_bins = 32 # Number of histogram bins
spatial_feat = True # Spatial features on or off
hist_feat = True # Histogram features on or off
hog_feat = True # HOG features on or off
y_start_stop = [450, 720] # Min and max in y to search in slide_window()
t=time.time()
car_features = extract_features(cars, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
notcar_features = extract_features(notcars, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
t2 = time.time()
print(round(t2-t, 2), 'Seconds to extract feature...')
#print('Num of car feature: ', len(car_features),', Num of not car feature: ', len(notcar_features))
X = np.vstack((car_features, notcar_features)).astype(np.float64)
# Fit a per-column scaler
X_scaler = StandardScaler().fit(X)
# Apply the scaler to X
scaled_X = X_scaler.transform(X)
# Define the labels vector
y = np.hstack((np.ones(len(car_features)), np.zeros(len(notcar_features))))
# Split up data into randomized training and test sets
rand_state = np.random.randint(0, 100)
X_train, X_test, y_train, y_test = train_test_split(
scaled_X, y, test_size=0.2, random_state=rand_state)
print('Using:','Color Space: ', color_space, ',', orient,'orientations',pix_per_cell,
'pixels per cell and', cell_per_block,'cells per block')
print('Feature vector length:', len(X_train[0]))
# Use a linear SVC
svc = LinearSVC()
# Check the training time for the SVC
t=time.time()
svc.fit(X_train, y_train)
t2 = time.time()
print(round(t2-t, 2), 'Seconds to train SVC...')
# Check the score of the SVC
print('Test Accuracy of SVC = ', round(svc.score(X_test, y_test), 4))
# Check the prediction time for a single sample
t=time.time()
image = mpimg.imread('cutouts/bbox-example-image.jpg')
draw_image = np.copy(image)
# Uncomment the following line if you extracted training
# data from .png images (scaled 0 to 1 by mpimg) and the
# image you are searching is a .jpg (scaled 0 to 255)
image = image.astype(np.float32)/255
windows = slide_window(image, x_start_stop=[None, None], y_start_stop=y_start_stop,
xy_window=(96, 96), xy_overlap=(0.5, 0.5))
hot_windows = search_windows(image, windows, svc, X_scaler, color_space=color_space,
spatial_size=spatial_size, hist_bins=hist_bins,
orient=orient, pix_per_cell=pix_per_cell,
cell_per_block=cell_per_block,
hog_channel=hog_channel, spatial_feat=spatial_feat,
hist_feat=hist_feat, hog_feat=hog_feat)
t2=time.time()
print(round(t2-t, 2), 'Seconds to Search Hot Windows...')
window_img = draw_boxes(draw_image, hot_windows, color=(0, 0, 255), thick=6)
plt.imshow(window_img)
plt.show()
In [9]:
# Define a single function that can extract features using hog sub-sampling and make predictions
def find_carsbbox(img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell, cell_per_block, spatial_size, hist_bins):
draw_img = np.copy(img)
img = img.astype(np.float32)/255
img_tosearch = img[ystart:ystop,:,:]
ctrans_tosearch = convert_color(img_tosearch, conv='RGB2YUV')
if scale != 1:
imshape = ctrans_tosearch.shape
ctrans_tosearch = cv2.resize(ctrans_tosearch, (np.int(imshape[1]/scale), np.int(imshape[0]/scale)))
ch1 = ctrans_tosearch[:,:,0]
ch2 = ctrans_tosearch[:,:,1]
ch3 = ctrans_tosearch[:,:,2]
# Define blocks and steps as above
nxblocks = (ch1.shape[1] // pix_per_cell) - cell_per_block + 1
nyblocks = (ch1.shape[0] // pix_per_cell) - cell_per_block + 1
nfeat_per_block = orient*cell_per_block**2
# 64 was the orginal sampling rate, with 8 cells and 8 pix per cell
window = 64
nblocks_per_window = (window // pix_per_cell) - cell_per_block + 1
cells_per_step = 2 # Instead of overlap, define how many cells to step
nxsteps = (nxblocks - nblocks_per_window) // cells_per_step
nysteps = (nyblocks - nblocks_per_window) // cells_per_step
# Compute individual channel HOG features for the entire image
hog1 = get_hog_features(ch1, orient, pix_per_cell, cell_per_block, feature_vec=False)
hog2 = get_hog_features(ch2, orient, pix_per_cell, cell_per_block, feature_vec=False)
hog3 = get_hog_features(ch3, orient, pix_per_cell, cell_per_block, feature_vec=False)
window_list = []
for xb in range(nxsteps):
for yb in range(nysteps):
ypos = yb*cells_per_step
xpos = xb*cells_per_step
# Extract HOG for this patch
hog_feat1 = hog1[ypos:ypos+nblocks_per_window, xpos:xpos+nblocks_per_window].ravel()
hog_feat2 = hog2[ypos:ypos+nblocks_per_window, xpos:xpos+nblocks_per_window].ravel()
hog_feat3 = hog3[ypos:ypos+nblocks_per_window, xpos:xpos+nblocks_per_window].ravel()
hog_features = np.hstack((hog_feat1, hog_feat2, hog_feat3))
xleft = xpos*pix_per_cell
ytop = ypos*pix_per_cell
# Extract the image patch
subimg = cv2.resize(ctrans_tosearch[ytop:ytop+window, xleft:xleft+window], (64,64))
# Get color features
spatial_features = bin_spatial(subimg, size=spatial_size)
hist_features = color_hist(subimg, nbins=hist_bins)
# Scale features and make a prediction
test_features = X_scaler.transform(np.hstack((spatial_features, hist_features, hog_features)).reshape(1, -1))
test_prediction = svc.predict(test_features)
if test_prediction == 1:
xbox_left = np.int(xleft*scale)
ytop_draw = np.int(ytop*scale)
win_draw = np.int(window*scale)
window_list.append(((xbox_left, ytop_draw+ystart), (xbox_left+win_draw, ytop_draw+win_draw+ystart)))
cv2.rectangle(draw_img,(xbox_left, ytop_draw+ystart),(xbox_left+win_draw,ytop_draw+win_draw+ystart),(0,0,255),6)
return draw_img, window_list
ystart = 360
ystop = 700
scale = 1.5
img = mpimg.imread('test_images/test1.jpg')
bb_img, box_list = find_carsbbox(img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell, cell_per_block, spatial_size, hist_bins)
plt.imshow(bb_img)
plt.show()
4. Multiple Detection & False Positives¶
In [12]:
from scipy.ndimage.measurements import label
# heatmap
heat = np.zeros_like(img[:,:,0]).astype(np.float)
def add_heat(heatmap, bbox_list):
# Iterate through list of bboxes
for box in bbox_list:
# Add += 1 for all pixels inside each bbox
# Assuming each "box" takes the form ((x1, y1), (x2, y2))
heatmap[box[0][1]:box[1][1], box[0][0]:box[1][0]] += 1
# Return updated heatmap
return heatmap# Iterate through list of bboxes
def apply_threshold(heatmap, threshold):
# Zero out pixels below the threshold
heatmap[heatmap <= threshold] = 0
# Return thresholded map
return heatmap
def draw_labeled_bboxes(img, labels):
# Iterate through all detected cars
for car_number in range(1, labels[1]+1):
# Find pixels with each car_number label value
nonzero = (labels[0] == car_number).nonzero()
# Identify x and y values of those pixels
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
# Define a bounding box based on min/max x and y
bbox = ((np.min(nonzerox), np.min(nonzeroy)), (np.max(nonzerox), np.max(nonzeroy)))
# Draw the box on the image
cv2.rectangle(img, bbox[0], bbox[1], (0,255,0), 6)
# Return the image
return img
# Add heat to each box in box list
heat = add_heat(heat,box_list)
# Apply threshold to help remove false positives
heat = apply_threshold(heat,1)
# Visualize the heatmap when displaying
heatmap = np.clip(heat, 0, 255)
# Find final boxes from heatmap using label function
labels = label(heatmap)
draw_img = draw_labeled_bboxes(np.copy(img), labels)
fig = plt.figure(figsize=(10,5))
plt.subplot(121)
plt.imshow(draw_img)
plt.title('Car Positions')
plt.subplot(122)
plt.imshow(heatmap, cmap='hot')
plt.title('Heat Map')
fig.tight_layout()
plt.show()
Apply to all the test images¶
In [11]:
images = glob.glob('test_images/test*.jpg')
images = sorted(images)
f, ax = plt.subplots(len(images), 3, figsize=(20, len(images)*5))
heatmap_threshold = 1
i = 0
for fname in images:
img = mpimg.imread(fname)
#bboxes
bb_img, box_list = find_carsbbox(img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell, cell_per_block, spatial_size, hist_bins)
ax[i][0].imshow(bb_img)
ax[i][0].set_title(fname.split('/')[-1], fontsize=20)
# Heatmap
heat = np.zeros_like(img[:,:,0]).astype(np.float)
heat = add_heat(heat, box_list)
heat = apply_threshold(heat, heatmap_threshold)
heatmap = np.clip(heat, 0, 255)
ax[i][1].imshow(heatmap, cmap='hot')
ax[i][1].set_title('Heatmap', fontsize=20)
# Find final boxes from heatmap using label function
labels = label(heatmap)
draw_img = draw_labeled_bboxes(np.copy(img), labels)
ax[i][2].imshow(draw_img)
ax[i][2].set_title('Car Position', fontsize=20)
i = i +1
plt.show()
5. Test on Videos¶
In [13]:
def process_image(img):
bb_img, box_list = find_carsbbox(img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell, cell_per_block, spatial_size, hist_bins)
heat = np.zeros_like(img[:,:,0]).astype(np.float)
heat = add_heat(heat, box_list)
heat = apply_threshold(heat, heatmap_threshold)
heatmap = np.clip(heat, 0, 255)
# Find final boxes from heatmap using label function
labels = label(heatmap)
out_img = draw_labeled_bboxes(np.copy(img), labels)
return out_img
In [14]:
# Import everything needed to edit/save/watch video clips
from moviepy.editor import VideoFileClip
from IPython.display import HTML
project_output = 'project_video_out.mp4'
## To speed up the testing process you may want to try your pipeline on a shorter subclip of the video
## To do so add .subclip(start_second,end_second) to the end of the line below
## Where start_second and end_second are integer values representing the start and end of the subclip
## You may also uncomment the following line for a subclip of the first 5 seconds
##clip1 = VideoFileClip("test_videos/solidWhiteRight.mp4").subclip(0,5)
clip1 = VideoFileClip("project_video.mp4")
output_clip = clip1.fl_image(process_image) #NOTE: this function expects color images!!
%time output_clip.write_videofile(project_output, audio=False)
In [15]:
HTML("""
<video width="960" height="540" controls>
<source src="{0}">
</video>
""".format(project_output))
Out[15]:
In [ ]: